ResearchDatasetsSimple AdversarySimple AdversaryFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-agent reinforcement learningSimple Adversary Heavy DBC-6.8Avg Episode Reward7Multi-agent reinforcement learningSimple Adversary Unrestricted-5.8Avg Episode Cumulative Reward7